Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1365 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Diagram Creation | CanvasBench (test) | 22 | Apr 14, 2026 | ||
| Logistic Regression | Toeplitz Sigma_a r=0.4 (synthetic) | 22 | Apr 14, 2026 | ||
| Visual Localization | Aachen Night | 22 | Apr 13, 2026 | ||
| Visual Localization | Aachen Day | 22 | Apr 13, 2026 | ||
| Visual Localization | IMC 2022 | 22 | Apr 13, 2026 | ||
| Text Classification | DBPedia-14 | 22 | May 14, 2026 | ||
| Activity Recognition | WESAD | 22 | May 18, 2026 | ||
| Flow Correlation | Tor traffic dataset | 22 | Apr 13, 2026 | ||
| Out-of-Distribution Detection | SSB HARD (test) | 22 | Apr 13, 2026 | ||
| Language-conditioned long-horizon robotic manipulation | CALVIN ABC→D | 22 | Jul 7, 2026 | ||
| 3D reconstruction | Oxford Spires | 22 | May 25, 2026 | ||
| Pose Estimation | Waymo | 22 | Jun 4, 2026 | ||
| Text-to-Video Generation | VideoPhy-2 | 22 | Jul 7, 2026 | ||
| Unlearning | DomainNet c → s | 22 | Apr 10, 2026 | ||
| Unlearning | DomainNet Sketch to Painting | 22 | Apr 10, 2026 | ||
| Long Video Understanding | Video-MME (w/o sub.) Overall 1010s | 22 | Apr 10, 2026 | ||
| Multimodal Large Language Model Evaluation | MME | 22 | Apr 24, 2026 | ||
| Classification | monk | 22 | Apr 10, 2026 | ||
| Multi-task Driver Monitoring | AIDE (test) | 22 | Apr 10, 2026 | ||
| Math Reasoning | Math Level-5 | 22 | Apr 8, 2026 | ||
| Text-centric Reasoning | VideoThinkBench mini (test) | 22 | Apr 8, 2026 | ||
| Global Relocalization | Degenerate Long Corridor Environment | 22 | Apr 8, 2026 | ||
| Commonsense Reasoning | Winogrande | 22 | May 21, 2026 | ||
| Language Modeling | LawStack LB | 22 | Apr 7, 2026 | ||
| General Multi-task Video Understanding | VideoMME w/o sub | 22 | Apr 7, 2026 |